Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to technology, particularly in the context of inventions or innovations

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence or intellectual concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tow
    -0.67
     trunk
    -0.63
     whales
    -0.60
     refuge
    -0.60
    bilt
    -0.59
     transitional
    -0.59
     downhill
    -0.59
     park
    -0.58
     bear
    -0.58
     Bundy
    -0.57
    POSITIVE LOGITS
    elligent
    1.58
    ellig
    1.56
    ellectual
    1.53
    ellect
    1.51
    angible
    1.41
    ended
    1.41
    ensive
    1.40
    elligence
    1.40
    imate
    1.40
    ention
    1.39
    Act Density 0.024%

    No Known Activations